Skills.
Give your AI a better way to work.
A skill is a set of written instructions that teaches an AI how to do one job the way it should be done: review a pull request, plan a migration, write the release notes.
Install one here and it travels with your account into Claude, Claude Code, Cursor and every other client you sign in with.
Filter by category
53,895 results · page 122 of 1,797
- View details
vulnerability-triage-brocardsSkillSecurity
Helps your agent triage and prioritize vulnerability reports like CVEs and bug bounty findings.
Ready to connect★ 7k
- View details
writing-lean-proofsSkillDev tools
Writes and reviews structured Lean 4 proofs and designs Lean libraries following Mathlib conventions. Use when proving theorems in Lean, formalizing mathematics or specifications in Lean 4, defining new types or definitions in a Lean library, reviewing Lean proofs for readability and maintainability
Ready to connect★ 7k
- View details
wycheproofSkillCommerce & finance
Lets your agent test cryptographic code against known attack test vectors for AES, RSA, ECDSA, and more.
Ready to connect★ 7k
- View details
yara-rule-authoringSkillSecurity
Guides your agent in writing and improving YARA rules that identify malware accurately.
Ready to connect★ 7k
- View details
zeroize-auditSkillDev tools
Lets your agent scan C, C++, or Rust code to find places where secrets like keys or passwords are not properly erased from memory.
Ready to connect★ 7k
- View details
paperbananaSkillDev tools
Lets your agent turn a paper's methodology text into publication-quality academic diagrams.
Ready to connect★ 7k
- View details
trailofbits:audit-contextSkillSecurity
Lets your agent build a deep map of a codebase's architecture before hunting for security vulnerabilities.
★ 7k
- View details
trailofbits:burp-searchSkillSearch
Lets your agent search Burp Suite project files to find details for security analysis.
★ 7k
- View details
trailofbits:ct-checkSkillCommerce & finance
Lets your agent scan cryptographic code for timing side-channel vulnerabilities.
★ 7k
- View details
trailofbits:diff-reviewSkillSecurity
Lets your agent review code changes for security problems by comparing what changed.
★ 7k
- View details
trailofbits:entry-pointsSkillDev tools
Lets your agent find the functions in a smart contract that can change its state.
★ 7k
- View details
trailofbits:scan-apkSkillSecurity
Lets your agent scan Android APK files for Firebase security misconfigurations.
★ 7k
- View details
trailofbits:semgrep-ruleSkillDev tools
Lets your agent write Semgrep code-scanning rules using a test-first approach.
★ 7k
- View details
trailofbits:spec-complianceSkillDev tools
Lets your agent check whether code actually implements the requirements written in a specification.
★ 7k
- View details
trailofbits:variantsSkillSecurity
Lets your agent scan code for patterns that match known vulnerability types to find similar security bugs.
★ 7k
- View details
build-brightstaffSkillDev tools
Lets your agent compile the brightstaff native binary after code changes.
Ready to connect★ 7k
- View details
build-cliSkillDev tools
Lets your agent build and install the planoai Python CLI locally after changes to the cli/ code.
Ready to connect★ 7k
- View details
build-wasmSkillDev tools
Lets your agent build WASM plugins for Envoy when plugin code changes.
Ready to connect★ 7k
- View details
checkSkillDev tools
Lets your agent run Rust formatting, clippy lint checks, and unit tests after code changes.
Ready to connect★ 7k
- View details
new-providerSkillAI & models
Lets your agent add a new AI model provider to hermesllm when you want to integrate one.
Ready to connect★ 7k
- View details
plano-advanced-patternsSkillMedia
Teaches your agent to design advanced Plano architectures with multi-listener systems and layered orchestration.
Ready to connect★ 7k
- View details
plano-agent-orchestrationSkillAI & models
Lets your agent register and wire up multiple agents in Plano so tasks get routed to the right one.
Ready to connect★ 7k
- View details
plano-agent-skillsSkillCloud & infra
Gives your agent guidance on building agentic apps with Plano, covering config, routing, guardrails, and deployment.
Ready to connect★ 7k
- View details
plano-cli-operationsSkillAI & models
Lets your agent troubleshoot Plano CLI startup issues, run agent workflows, and create projects from templates.
Ready to connect★ 7k
- View details
plano-config-fundamentalsSkillDev tools
Lets your agent validate and fix Plano configuration files, covering versioning, listeners, providers, and startup errors.
Ready to connect★ 7k
- View details
plano-deployment-securitySkillFiles & storage
Guides your agent through Plano deployment setup, covering Docker networking, storage, readiness checks, and secret handling.
Ready to connect★ 7k
- View details
plano-filter-guardrailsSkillAI & models
Lets your agent set up and tune Plano filter chains, prompt guardrails, and safe filter ordering.
Ready to connect★ 7k
- View details
plano-observability-debuggingSkillMonitoring & ops
Lets your agent analyze Plano traces to find root causes and improve tracing and debugging.
Ready to connect★ 7k
- View details
plano-routing-model-selectionSkillAI & models
Lets your agent configure which AI models get chosen and routed for requests, including defaults, aliases, and preferences.
Ready to connect★ 7k
- View details
test-pythonSkillDev tools
Lets your agent run Python command-line tests to check code changes.
Ready to connect★ 7k
What is a skill?
A skill is plain text, usually a SKILL.md file and the scripts it refers to, written for an AI rather than for a person. It carries the steps, the house rules and the examples a good answer needs, so you stop pasting the same briefing into every new chat.
53,462 of the 53,895 skills listed here can be served through ahel today, and they come from public repositories. Each one has its own page with the instructions themselves on it, so you can read what a skill will tell your AI to do before you install it.
Install one and every AI you use gets it
Installing a skill adds it to your gateway and turns it on in the same step. Claude Code surfaces it as a slash command; any client can read the full instructions with the skill_read tool.
Nothing is copied into a project folder. The instructions are served from your account, so the same skill is there in every AI you connect, and turning it off removes it from all of them at once.